# Mitigating Legibility Tax with Decoupled Prover-Verifier Games

arXiv: https://arxiv.org/abs/2602.23248 · HTML: https://mlsanity.com/paper/2602.23248/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [Implicit Chain of Thought Reasoning via Knowledge Distillation](https://mlsanity.com/paper/2311.01460/) (2023)
- [Prover-Verifier Games improve legibility of LLM outputs](https://mlsanity.com/paper/2407.13692/) (2024)
- [Learning to Give Checkable Answers with Prover-Verifier Games](https://mlsanity.com/paper/2108.12099/) (2021)

## Built on by (most cited first, 1 of 1)

- [Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality](https://mlsanity.com/paper/2604.04418/) (2026)

## Abstract (arXiv)

As large language models become increasingly capable, it is critical that their outputs can be easily checked by less capable systems. Prover-verifier games can be used to improve checkability of model outputs, but display a degradation in accuracy compared to a baseline trained only to maximize correctness -- a phenonemon named legibility tax. We propose a solution by decoupling the correctness from the checkability condition and instead training a "translator" model that turns a fixed solver model's solution into a checkable form. This allows us to first train the solver to maximize correctness, and then train the translator to translate the solver into a checkable form while retaining the solver's answer. To accommodate this new objective of translation, we formulate a decoupled prover-verifier game (DPVG) where the equilibria correspond to faithful and checkable translators.